OpenAI: GPT-4 Turbo

Compact GPT model for low-latency assistance and high-volume workloads

Model lab: OpenAI
Model family: gpt

Modalitiestext, image → text

Context window128,000

Maximum output4,096

InputUSD 8 / 1M tokens

OutputUSD 24 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/openai/gpt-4-turbo.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/openai/gpt-4-turbo"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

GPT-4 Turbo API Pricing

Type	Price information
Input	USD 8 / 1M tokens
Output	USD 24 / 1M tokens

Benchmarks

Intelligence Index · v4.37

Coding Index21.5

Agentic Index—

Benchmark	Score	Measurement	Source
Artificial Analysis Coding Index	21.5	index · Date: 2026-03-11
SciCode	31.9	percent correct · Date: 2026-03-11

Performance

Output speed32.46 tokens/s

Time to first token3.17 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput32.46 tok/sCurrent

Time to first token3.17 sCurrent

End-to-end latency7.7 sCurrent

Throughput

Current32.46 tok/s

Window average31.6 tok/s

Time to first token

Current3.17 s

Window average3.3 s

End-to-end latency

Current7.7 s

Window average7.5 s

Tail latency (P99)

Current17.5 s

Window average16.9 s

Prompt cache hit rate

Current31.2%

Window average22.7%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

GPT-4 Turbo Compare models

Model	Input price	Output price	Context window	Capabilities
GPT-4 TurboThis page	USD 8 / 1M tokens	USD 24 / 1M tokens	128,000	Text output · Tool calling
GPT-5.6 Cyber	USD 10 / 1M tokens	USD 60 / 1M tokens	400,000	Text output · Reasoning · Tool calling
GPT-5.3 Chat (latest)	USD 1.4 / 1M tokens	USD 11.2 / 1M tokens	128,000	Text output · Tool calling
GPT-5.2	USD 0.7 / 1M tokens · Service tier flex	USD 5.6 / 1M tokens · Service tier flex	400,000	Text output · Reasoning · Tool calling
GPT-5.1	USD 0.5 / 1M tokens · Service tier flex	USD 4 / 1M tokens · Service tier flex	400,000	Text output · Reasoning · Tool calling

Model specifications

Input: text, image
Output: text
Context window: 128,000
Maximum output: 4,096
Release date: 2023-11-06
Attachments: Yes
Reasoning: No
Tool calling: Yes
Structured output: No
Temperature setting: Yes
Open weights: No

Frequently asked questions

What is GPT-4 Turbo for?

Compact GPT model for low-latency assistance and high-volume workloads

What inputs and outputs does GPT-4 Turbo support?

Recorded inputs: text, images; outputs: text.

How is GPT-4 Turbo priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 8 / 1M tokens; Output USD 24 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for GPT-4 Turbo?

Current model records list Context window 128,000 tokens; Maximum output 4,096 tokens.

What model parameter does the Quickstart use?

The example uses moduck/openai/gpt-4-turbo. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.